Developer documentation

Everything you need to integrate JPEG Trust into your applications — the Python package, the REST API, trust profiles, and compliance guides.

What is JPEG Trust?

JPEG Trust (ISO/IEC 21617) is a provenance system for images. It embeds cryptographically signed metadata — who created an image, how it was edited, whether AI was involved — directly into the file using the JUMBF container format. Downstream consumers can then verify that metadata against configurable trust profiles.

Architecture

The JPEG Trust system has two layers: a consumer web UI for visual workflows, and a developer SDK for programmatic access.

System architecture
Consumer layer
Web UI
↓
Upload / verify / create profiles
Developer layer
jpegtrust SDK
↓
Python API + CLI
↓
Embed / extract / verify / batch
JUMBF engine

Packages

🐍 Python package Install the Python library and CLI. Embed, extract, and verify from code or the terminal. 🦀 Rust Crate A native Rust library and CLI — a faithful, binary-compatible port of the Python package.

Get started

⚡ REST API Integrate over HTTP with multipart requests. Interactive Swagger and ReDoc explorers included.

Guides

Embedding Inject provenance metadata into JPEG and PNG images. Verification Validate images against trust profiles and read scored reports. Profile creation Configure trust assertions and export profile YAML files. Batch workflows Process entire directories of images at once. Custom profiles Write your own checks and expressions for specialised workflows. Use cases Newsroom, insurance, AI labelling, and creator workflows.

Alignment with Compliance

🌎 AI Content Transparency Around the World Three major regimes now set the pace for AI-content transparency: the EU AI Act, California's AI Transparency Act, and China's AI-generated synthetic content labelling framework. They share a common core — signed, machine-readable provenance plus human-facing disclosure — but diverge on visible labels, prescribed metadata fields, detection tooling and platform duties. JPEG Trust provides technical building blocks that map onto all three.
🛡 Art. 50 — Transparency How JPEG Trust helps you meet EU AI Act Article 50 requirements for AI-generated content labelling. 🛡 Art. 53 — GPAI Models Article 53 sets documentation and transparency requirements for providers of general-purpose AI (GPAI) models. JPEG Trust helps satisfy these obligations by providing machine-readable provenance metadata that documents model involvement, training data declarations, and copyright compliance. 🛡 California AI Transparency Act Latent disclosures, a free public detection tool with an API, optional visible labels, platform preservation (2027) and capture-device provenance (2028). 🛡 China AI Labelling Measures Both explicit (visible) and implicit (metadata) labels, prescribed TC260 fields, user declarations and platform propagation information.